Wind turbine generator bearing fault diagnosing method based on deep joint adaptation network

Abstract

The invention discloses a wind turbine generator bearing fault diagnosing method based on a deep joint adaptation network. The wind turbine generator bearing fault diagnosing method based on the deepjoint adaptation network comprises the following steps: 1), establishing a multi-element fusion database; 2), establishing a deep joint adaptation model; 3), establishing a wind turbine generator bearing fault diagnosing model of the deep joint adaptation network; 4), establishing a multi-GPU cluster computing system. With the wind turbine generator bearing fault diagnosing method, according to distribution difference characteristics between training data and target data during monitoring under different actual working conditions, an inter-domain invariant characteristic representing and probability distribution difference correcting mechanism is explored, a fault target recognition strategy based on an inter-domain joint distribution adaptation and common characteristic deep learning fusion mechanism is provided, advantages of a deep self-encoding network can be utilized, the characteristics are not required to be artificially selected, better, abstract and advanced characteristics can be automatically extracted, and the computational complexity of a classification algorithm is reduced; the wind turbine generator bearing fault diagnosing method is especially suitable for a multi-noise, large-data, complex-structure and dynamic system.

Description

Technical field [0001] The invention relates to the field of wind power, in particular to a method for diagnosing faults of a wind turbine bearing based on a deep joint adaptation network. Background technique [0002] The bearing transmission system plays the role of power transmission, speed change, and speed regulation in the wind power system. It is one of the most important systems in the power transmission part of the wind power system. At the same time, due to uninterrupted use, it is also extremely prone to failure. Discovery and treatment in time will lead to paralysis of the entire system, which will greatly affect production efficiency. Therefore, in order to find faults in time, it is necessary to carry out reasonable, reliable and fast fault diagnosis of the bearing transmission system. [0003] Currently, the commonly used fault feature extraction methods mainly include wavelet transform, fast Fourier transform (Fast Fourier Transform, FFT for short), machine learnin...

AI Technical Summary

Problems solved by technology

And all the above-mentioned fault feature extraction methods not only have their own shortcomings, but also can obtain good diagnostic results based on an assumption, that is, the original training data set and the target data set obey the same distribution, and in the actual working environment of the system, it is Difficult to meet, so it is impossible to use the existing fault characteristics under different working conditions to realize the diagnosis of new bearing faults

Images